Experimental demonstration of quantum learning speed-up with classical input data

Abstract

We consider quantum-classical hybrid machine learning in which large-scale input channels remain classical and small-scale working channels process quantum operations conditioned on classical input data. This does not require the conversion of classical (big) data to a quantum superposed state, in contrast to recently developed approaches for quantum machine learning. We performed optical experiments to illustrate a single-bit universal machine, which can be extended to a large-bit circuit for binary classification task. Our experimental machine exhibits quantum learning speed-up of approximately 36%, as compared to the fully classical machine. In addition, it features strong robustness against dephasing noise.

submitted

References in corpus (12)

• Quantum algorithm for solving linear systems of equations
• An introduction to quantum machine learning
• Quantum random access memory
• Quantum machine learning: a classical perspective
• Quantum-enhanced machine learning
• Architectures for a quantum random access memory
• Quantum generalisation of feedforward neural networks
• Experimental Realization of Quantum Artificial Intelligence
• Quantum machine learning for quantum anomaly detection
• Computational speedups using small quantum devices
• An All-Pair Quantum SVM Approach for Big Data Multiclass Classification
• Quantum Learning Machine

Cited by in corpus (5)

• Adiabatic Quantum Kitchen Sinks for Learning Kernels Using Randomized Features
• Quantum neural compressive sensing for ghost imaging
• Quantum secure learning with classical samples
• Tangible reduction in learning sample complexity with large classical samples and small quantum system
• Ensuring superior learning outcomes and data security for authorized learner